Triple
T13015255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sondra Huxtable |
E322533
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Elvin Tibideaux |
E1021940
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Elvin Tibideaux | Statement: [Sondra Huxtable, spouse, Elvin Tibideaux]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elvin Tibideaux Context triple: [Sondra Huxtable, spouse, Elvin Tibideaux]
-
A.
Jeffrey Skiles
Jeffrey Skiles is an American airline pilot best known as the first officer who helped safely land US Airways Flight 1549 on the Hudson River alongside Captain Chesley "Sully" Sullenberger.
-
B.
Nelson Tibideaux
chosen
Nelson Tibideaux is a minor character on the sitcom "The Cosby Show," known as one of the twin sons of Sondra Huxtable and Elvin Tibideaux.
-
C.
Roger Clemons
Roger Clemons is an individual best known as the person associated with the use of the entity named Clemons.
-
D.
Joe Jamail
Joe Jamail was a prominent American trial lawyer and billionaire philanthropist from Texas, often called the “King of Torts” for his record-setting courtroom victories.
-
E.
Rene Mathis
René Mathis is a recurring French intelligence ally of James Bond in Ian Fleming’s 007 novels and their adaptations.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d807657e8c8190bd9435ee2f823845 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97ecd04748190ade2530ee5db35fe |
completed | April 10, 2026, 10:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6f5c5155c8190b2c4e5bbcdaadc47 |
completed | May 3, 2026, 7:14 a.m. |
Created at: April 9, 2026, 8:50 p.m.